Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    after

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wakati
    0.52
    সাথে
    0.42
     товары
    0.42
    ｻ
    0.42
     stesse
    0.42
    場合があります
    0.41
    အတူ
    0.40
     гульнявыя
    0.39
     maaaring
    0.38
     proté
    0.38
    POSITIVE LOGITS
     after
    0.74
     After
    0.71
     selesai
    0.71
    After
    0.67
     после
    0.66
     nakon
    0.64
     після
    0.63
     después
    0.63
     Après
    0.62
     setelah
    0.60
    Act Density 0.088%

    No Known Activations